The Annals of Applied Statistics
- Ann. Appl. Stat.
- Volume 9, Number 2 (2015), 754-776.
Goodness of fit in nonlinear dynamics: Misspecified rates or misspecified states?
This paper introduces diagnostic tests for the nature of lack of fit in ordinary differential equation models (ODEs) proposed for data. We present a hierarchy of three possible sources of lack of fit: unaccounted-for stochastic variation, misspecification of functional forms in rate equations, and omission of dynamic variables in the description of the system. We represent lack of fit by allowing a parameter vector to vary over time, and propose generic testing procedures that do not rely on specific alternative models. Instead, different sources for lack of fit are characterized in terms of nonparametric relationships among latent variables. The tests are carried out through a combination of residual bootstrap and permutation methods. We demonstrate the effectiveness of these tests on simulated data and on real data from laboratory ecological experiments and electro-cardiogram data.
Ann. Appl. Stat. Volume 9, Number 2 (2015), 754-776.
Received: December 2013
Revised: December 2014
First available in Project Euclid: 20 July 2015
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Hooker, Giles; Ellner, Stephen P. Goodness of fit in nonlinear dynamics: Misspecified rates or misspecified states?. Ann. Appl. Stat. 9 (2015), no. 2, 754--776. doi:10.1214/15-AOAS828. https://projecteuclid.org/euclid.aoas/1437397110.
- Supplementary material for “Goodness of fit in nonlinear dynamics: Misspecified rates or misspecified states?”. This appendix provides supporting material which includes the following: details of the chemostat models used to generate data for Section 6 and background material on the generalized profiling methods of Ramsay et al. (2007), along with simulation experiments using this method instead of gradient matching.